Summary of Interpretable Breast Cancer Classification Using Cnns on Mammographic Images, by Ann-kristin Balve et al.
Interpretable breast cancer classification using CNNs on mammographic images
by Ann-Kristin Balve, Peter Hendrix
First submitted to arxiv on: 23 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Deep learning models have achieved promising results in breast cancer classification, but their ‘black-box’ nature raises interpretability concerns. This research addresses the crucial need to gain insights into the decision-making process of convolutional neural networks (CNNs) for mammogram classification, specifically focusing on the underlying reasons for the CNN’s predictions of breast cancer. The study compares post-hoc interpretability techniques LIME, Grad-CAM, and Kernel SHAP in terms of explanatory depth and computational efficiency using the Mammographic Image Analysis Society (MIAS) dataset. The results indicate that Grad-CAM provides comprehensive insights into the behavior of the CNN, revealing distinctive patterns in normal, benign, and malignant breast tissue. This study has implications for the use of machine learning models and interpretation techniques in clinical practice. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Deep learning models are really good at classifying breast cancer from mammograms, but we don’t know why they’re making those predictions. This research tries to figure out what’s going on inside these models by looking at different ways to understand how they work. They compared three methods: LIME, Grad-CAM, and Kernel SHAP. The results show that one method, Grad-CAM, is really good at showing us what the model is looking at in different types of breast tissue. This study helps us understand how we can use these models in real life. |
Keywords
» Artificial intelligence » Classification » Cnn » Deep learning » Machine learning
